{"ID":2877813,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.20277","arxiv_id":"2508.20277","title":"Error Analysis for Over-the-Air Federated Learning under Misaligned and Time-Varying Channels","abstract":"This paper investigates an OFDM-based over-the-air federated learning (OTA-FL) system, where multiple mobile devices, e.g., unmanned aerial vehicles (UAVs), transmit local machine learning (ML) models to a central parameter server (PS) for global model aggregation. The high mobility of local devices results in imperfect channel estimation, leading to a misalignment problem, i.e., the model parameters transmitted from different local devices do not arrive at the central PS simultaneously. Moreover, the mobility introduces time-varying uploading channels, which further complicates the aggregation process. All these factors collectively cause distortions in the OTA-FL training process which are underexplored. To quantify these effects, we first derive a closed-form expression for a single-round global model update in terms of these channel imperfections. We then extend our analysis to capture multiple rounds of global updates, yielding a bound on the accumulated error in OTA-FL. We validate our theoretical results via extensive numerical simulations, which corroborate our derived analysis.","short_abstract":"This paper investigates an OFDM-based over-the-air federated learning (OTA-FL) system, where multiple mobile devices, e.g., unmanned aerial vehicles (UAVs), transmit local machine learning (ML) models to a central parameter server (PS) for global model aggregation. The high mobility of local devices results in imperfec...","url_abs":"https://arxiv.org/abs/2508.20277","url_pdf":"https://arxiv.org/pdf/2508.20277v1","authors":"[\"Xiaoyan Ma\",\"Shahryar Zehtabi\",\"Taejoon Kim\",\"Christopher G. Brinton\"]","published":"2025-08-27T21:19:54Z","proceeding":"eess.SP","tasks":"[\"eess.SP\"]","methods":"[]","has_code":false}